ai-forever commited on
Commit
cc20058
1 Parent(s): 0fb1ca9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -6
README.md CHANGED
@@ -87,18 +87,42 @@ We reproduce the GPT-3 architecture using GPT-2 sources and the sparse attention
87
  The source code for the mGPT XL model is available on [Github](https://github.com/sberbank-ai/mgpt)
88
 
89
  ## Paper
90
- [Arxiv preprint](https://arxiv.org/user)
 
 
91
 
92
- Cite us:
93
- ```{
94
- bibtex
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95
  }
96
- ```
 
 
97
 
98
  ## Languages
99
 
100
- Model includes 60 languages: (iso codes)
 
101
  ```az, sw, af, ar, ba, be, bxr, bg, bn, cv, hy, da, de, el, es, eu, fa, fi, fr, he, hi, hu, kk, id, it, ja, ka, ky, ko, lt, lv, mn, ml, os, mr, ms, my, nl, ro, pl, pt, sah, ru, tg, sv, ta, te, tk, th, tr, tl, tt, tyv, uk, en, ur, vi, uz, yo, zh, xal```
 
 
 
102
 
103
  ## Training Data Statistics
104
 
 
87
  The source code for the mGPT XL model is available on [Github](https://github.com/sberbank-ai/mgpt)
88
 
89
  ## Paper
90
+ mGPT: Few-Shot Learners Go Multilingual
91
+
92
+ [Abstract](https://arxiv.org/abs/2204.07580) [PDF](https://arxiv.org/pdf/2204.07580.pdf)
93
 
94
+ ![](https://habrastorage.org/webt/1q/ru/yt/1qruytul6m2m-upyk9frq3pgrds.png)
95
+
96
+ ```
97
+ @misc{https://doi.org/10.48550/arxiv.2204.07580,
98
+ doi = {10.48550/ARXIV.2204.07580},
99
+
100
+ url = {https://arxiv.org/abs/2204.07580},
101
+
102
+ author = {Shliazhko, Oleh and Fenogenova, Alena and Tikhonova, Maria and Mikhailov, Vladislav and Kozlova, Anastasia and Shavrina, Tatiana},
103
+
104
+ keywords = {Computation and Language (cs.CL), Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences, I.2; I.2.7, 68-06, 68-04, 68T50, 68T01},
105
+
106
+ title = {mGPT: Few-Shot Learners Go Multilingual},
107
+
108
+ publisher = {arXiv},
109
+
110
+ year = {2022},
111
+
112
+ copyright = {Creative Commons Attribution 4.0 International}
113
  }
114
+
115
+ ```
116
+
117
 
118
  ## Languages
119
 
120
+ Model supports 60 languages:
121
+ ISO codes:
122
  ```az, sw, af, ar, ba, be, bxr, bg, bn, cv, hy, da, de, el, es, eu, fa, fi, fr, he, hi, hu, kk, id, it, ja, ka, ky, ko, lt, lv, mn, ml, os, mr, ms, my, nl, ro, pl, pt, sah, ru, tg, sv, ta, te, tk, th, tr, tl, tt, tyv, uk, en, ur, vi, uz, yo, zh, xal```
123
+ Languages:
124
+ ```Afrikaans, Azerbaijani, Belarusian, Bengali, Chuvash, German, English, Basque, Finnish, Hebrew (modern), Hungarian, Indonesian, Japanese, Kazakh, Kirghiz, Kyrgyz, Latvian, Mongolian, Malay, Dutch, Polish, Romanian, Moldavan, Yakut, Swahili, Telugu, Thai, Turkish, Tuvinian, Urdu, Vietnamese, Yoruba, Arabic, Bashkir, Bulgarian, Buriat, Danish, Greek, Modern, Spanish; Castilian, Persian, French, Hindi, Armenian, Italian, Georgian, Korean, Lithuanian, Malayalam, Marathi, Burmese, Ossetian, Ossetic, Portuguese, Russian, Swedish, Tamil, Tajik, Turkmen, Tatar, Ukrainian, Uzbek, Kalmyk, Chinese
125
+ ```
126
 
127
  ## Training Data Statistics
128